fire

fire copied to clipboard

dear naver, great work with image retieval, I am so interested on your work, and want to try it on other datasets like imagenet-1k( and I saw you have imagenet-1k...

Chaoran-F

Thanks for your great work! I try to train the model on my pc but report cuda out of memory. My GPU is 3060Ti with 8GB memory.

aruba01

Hi, thanks for making the gradio demo here: https://huggingface.co/spaces/naver/SuperFeatures, great work. Would you be interested in updating the demo for the gradio blocks competition this month: https://huggingface.co/Gradio-Blocks or to add...

AK391

nice work. https://github.com/naver/fire/blob/main/losses.py#L46 ``` dist2_second2 = torch.argmin(dist2, dim=0) ratio1to2 = dist[best2,arange] / dist2_second2. # should it be dist[best2,arange] /dist2[dist2_second2:arange] ? ```

sysuzyq

I download the trained model fire.pth and just run : `python evaluate.py eval_fire.yml ` Testing open source data roxford5k and rparis6k. But I can not get the results mentioned in...

TouchSkyWf